Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
Yahong Wang, Juncheng Wu, Zhangkai Ni +8
Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising s…
cs.CV2024
DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
Juncheng Wu, Zhangkai Ni, Hanli Wang +3
Image deep features extracted by pre-trained networks are known to contain rich and informative representations. In this paper, we present Deep Degradation Response (DDR), a method…